external/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-10 01:02:13 +01:00
Code Issues Projects Releases Packages Wiki Activity

[compat] Remove more functions

Browse source 
Removing any more will require changes to a large number of extractors
This commit is contained in:
pukkandan 2022-06-24 13:40:17 +05:30
parent 3c5386cd71
commit ac66811112
No known key found for this signature in database
GPG key ID: 7EEE9E1E817D0A39
59 changed files with 392 additions and 486 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
devscripts/check-porn.py
View file

@ -13,9 +13,11 @@
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import gettestcases
from yt_dlp.utils import compat_urllib_parse_urlparse, compat_urllib_request
import urllib.request
from test.helper import gettestcases
from yt_dlp.utils import compat_urllib_parse_urlparse
if len(sys.argv) > 1:
METHOD = 'LIST'
@ -26,7 +28,7 @@
for test in gettestcases():
if METHOD == 'EURISTIC':
try:
webpage = compat_urllib_request.urlopen(test['url'], timeout=10).read()
webpage = urllib.request.urlopen(test['url'], timeout=10).read()
except Exception:
print('\nFail: {}'.format(test['name']))
continue

11
devscripts/update-formulae.py
View file

@ -1,12 +1,15 @@
#!/usr/bin/env python3
import json
# Allow direct execution
import os
import re
import sys
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from yt_dlp.compat import compat_urllib_request
import json
import re
import urllib.request
# usage: python3 ./devscripts/update-formulae.py <path-to-formulae-rb> <version>
# version can be either 0-aligned (yt-dlp version) or normalized (PyPl version)
@ -15,7 +18,7 @@
normalized_version = '.'.join(str(int(x)) for x in version.split('.'))
pypi_release = json.loads(compat_urllib_request.urlopen(
pypi_release = json.loads(urllib.request.urlopen(
'https://pypi.org/pypi/yt-dlp/%s/json' % normalized_version
).read().decode())

12
test/test_InfoExtractor.py
View file

@ -6,10 +6,12 @@
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import threading
from test.helper import FakeYDL, expect_dict, expect_value, http_server_port
from yt_dlp.compat import compat_etree_fromstring, compat_http_server
import http.server
import threading
from test.helper import FakeYDL, expect_dict, expect_value, http_server_port
from yt_dlp.compat import compat_etree_fromstring
from yt_dlp.extractor import YoutubeIE, get_info_extractor
from yt_dlp.extractor.common import InfoExtractor
from yt_dlp.utils import (
@ -23,7 +25,7 @@
TEAPOT_RESPONSE_BODY = "<h1>418 I'm a teapot</h1>"
class InfoExtractorTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
class InfoExtractorTestRequestHandler(http.server.BaseHTTPRequestHandler):
def log_message(self, format, *args):
pass
@ -1655,7 +1657,7 @@ def test_response_with_expected_status_returns_content(self):
# or the underlying `_download_webpage_handle` returning no content
# when a response matches `expected_status`.
httpd = compat_http_server.HTTPServer(
httpd = http.server.HTTPServer(
('127.0.0.1', 0), InfoExtractorTestRequestHandler)
port = http_server_port(httpd)
server_thread = threading.Thread(target=httpd.serve_forever)

18
test/test_YoutubeDL.py
View file

@ -8,15 +8,11 @@
import copy
import json
from test.helper import FakeYDL, assertRegexpMatches
import urllib.error
from test.helper import FakeYDL, assertRegexpMatches
from yt_dlp import YoutubeDL
from yt_dlp.compat import (
compat_os_name,
compat_setenv,
compat_str,
compat_urllib_error,
)
from yt_dlp.compat import compat_os_name, compat_str
from yt_dlp.extractor import YoutubeIE
from yt_dlp.extractor.common import InfoExtractor
from yt_dlp.postprocessor.common import PostProcessor
@ -841,14 +837,14 @@ def gen():
# test('%(foo|)s', ('', '_')) # fixme
# Environment variable expansion for prepare_filename
compat_setenv('__yt_dlp_var', 'expanded')
os.environ['__yt_dlp_var'] = 'expanded'
envvar = '%__yt_dlp_var%' if compat_os_name == 'nt' else '$__yt_dlp_var'
test(envvar, (envvar, 'expanded'))
if compat_os_name == 'nt':
test('%s%', ('%s%', '%s%'))
compat_setenv('s', 'expanded')
os.environ['s'] = 'expanded'
test('%s%', ('%s%', 'expanded')) # %s% should be expanded before escaping %s
compat_setenv('(test)s', 'expanded')
os.environ['(test)s'] = 'expanded'
test('%(test)s%', ('NA%', 'expanded')) # Environment should take priority over template
# Path expansion and escaping
@ -1101,7 +1097,7 @@ def test_selection(params, expected_ids, evaluate_all=False):
def test_urlopen_no_file_protocol(self):
# see https://github.com/ytdl-org/youtube-dl/issues/8227
ydl = YDL()
self.assertRaises(compat_urllib_error.URLError, ydl.urlopen, 'file:///etc/passwd')
self.assertRaises(urllib.error.URLError, ydl.urlopen, 'file:///etc/passwd')
def test_do_not_override_ie_key_in_url_transparent(self):
ydl = YDL()

29
test/test_compat.py
View file

@ -7,16 +7,15 @@
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import struct
import urllib.parse
from yt_dlp import compat
from yt_dlp.compat import (
compat_etree_fromstring,
compat_expanduser,
compat_getenv,
compat_setenv,
compat_str,
compat_struct_unpack,
compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus,
compat_urllib_parse_urlencode,
)
@ -31,26 +30,14 @@ def test_compat_passthrough(self):
compat.asyncio.events # Must not raise error
def test_compat_getenv(self):
test_str = 'тест'
compat_setenv('yt_dlp_COMPAT_GETENV', test_str)
self.assertEqual(compat_getenv('yt_dlp_COMPAT_GETENV'), test_str)
def test_compat_setenv(self):
test_var = 'yt_dlp_COMPAT_SETENV'
test_str = 'тест'
compat_setenv(test_var, test_str)
compat_getenv(test_var)
self.assertEqual(compat_getenv(test_var), test_str)
def test_compat_expanduser(self):
old_home = os.environ.get('HOME')
test_str = R'C:\Documents and Settings\тест\Application Data'
try:
compat_setenv('HOME', test_str)
os.environ['HOME'] = test_str
self.assertEqual(compat_expanduser('~'), test_str)
finally:
compat_setenv('HOME', old_home or '')
os.environ['HOME'] = old_home or ''
def test_compat_urllib_parse_unquote(self):
self.assertEqual(compat_urllib_parse_unquote('abc%20def'), 'abc def')
@ -72,8 +59,8 @@ def test_compat_urllib_parse_unquote(self):
'''(^◣_◢^)っ︻デ═一 ⇀ ⇀ ⇀ ⇀ ⇀ ↶%I%Break%Things%''')
def test_compat_urllib_parse_unquote_plus(self):
self.assertEqual(compat_urllib_parse_unquote_plus('abc%20def'), 'abc def')
self.assertEqual(compat_urllib_parse_unquote_plus('%7e/abc+def'), '~/abc def')
self.assertEqual(urllib.parse.unquote_plus('abc%20def'), 'abc def')
self.assertEqual(urllib.parse.unquote_plus('%7e/abc+def'), '~/abc def')
def test_compat_urllib_parse_urlencode(self):
self.assertEqual(compat_urllib_parse_urlencode({'abc': 'def'}), 'abc=def')
@ -107,7 +94,7 @@ def test_compat_etree_fromstring_doctype(self):
compat_etree_fromstring(xml)
def test_struct_unpack(self):
self.assertEqual(compat_struct_unpack('!B', b'\x00'), (0,))
self.assertEqual(struct.unpack('!B', b'\x00'), (0,))
if __name__ == '__main__':

21
test/test_download.py
View file

@ -1,14 +1,18 @@
#!/usr/bin/env python3
# Allow direct execution
import hashlib
import json
import os
import socket
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import hashlib
import json
import socket
import urllib.error
import http.client
from test.helper import (
assertGreaterEqual,
expect_info_dict,
@ -19,13 +23,8 @@
report_warning,
try_rm,
)
import yt_dlp.YoutubeDL
from yt_dlp.compat import (
compat_http_client,
compat_HTTPError,
compat_urllib_error,
)
import yt_dlp.YoutubeDL # isort: split
from yt_dlp.compat import compat_HTTPError
from yt_dlp.extractor import get_info_extractor
from yt_dlp.utils import (
DownloadError,
@ -167,7 +166,7 @@ def try_rm_tcs_files(tcs=None):
force_generic_extractor=params.get('force_generic_extractor', False))
except (DownloadError, ExtractorError) as err:
# Check if the exception is not a network related one
if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError, compat_http_client.BadStatusLine) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):
if not err.exc_info[0] in (urllib.error.URLError, socket.timeout, UnavailableVideoError, http.client.BadStatusLine) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):
raise
if try_num == RETRIES:

9
test/test_downloader_http.py
View file

@ -1,17 +1,18 @@
#!/usr/bin/env python3
# Allow direct execution
import os
import re
import sys
import unittest
import http.server
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import re
import threading
from test.helper import http_server_port, try_rm
from yt_dlp import YoutubeDL
from yt_dlp.compat import compat_http_server
from yt_dlp.downloader.http import HttpFD
from yt_dlp.utils import encodeFilename
@ -21,7 +22,7 @@
TEST_SIZE = 10 * 1024
class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
class HTTPTestRequestHandler(http.server.BaseHTTPRequestHandler):
def log_message(self, format, *args):
pass
@ -78,7 +79,7 @@ def error(self, msg):
class TestHttpFD(unittest.TestCase):
def setUp(self):
self.httpd = compat_http_server.HTTPServer(
self.httpd = http.server.HTTPServer(
('127.0.0.1', 0), HTTPTestRequestHandler)
self.port = http_server_port(self.httpd)
self.server_thread = threading.Thread(target=self.httpd.serve_forever)

20
test/test_http.py
View file

@ -3,20 +3,22 @@
import os
import sys
import unittest
import http.server
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import ssl
import threading
import urllib.request
from test.helper import http_server_port
from yt_dlp import YoutubeDL
from yt_dlp.compat import compat_http_server, compat_urllib_request
TEST_DIR = os.path.dirname(os.path.abspath(__file__))
class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
class HTTPTestRequestHandler(http.server.BaseHTTPRequestHandler):
def log_message(self, format, *args):
pass
@ -53,7 +55,7 @@ def error(self, msg):
class TestHTTP(unittest.TestCase):
def setUp(self):
self.httpd = compat_http_server.HTTPServer(
self.httpd = http.server.HTTPServer(
('127.0.0.1', 0), HTTPTestRequestHandler)
self.port = http_server_port(self.httpd)
self.server_thread = threading.Thread(target=self.httpd.serve_forever)
@ -64,7 +66,7 @@ def setUp(self):
class TestHTTPS(unittest.TestCase):
def setUp(self):
certfn = os.path.join(TEST_DIR, 'testcert.pem')
self.httpd = compat_http_server.HTTPServer(
self.httpd = http.server.HTTPServer(
('127.0.0.1', 0), HTTPTestRequestHandler)
sslctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
sslctx.load_cert_chain(certfn, None)
@ -90,7 +92,7 @@ def setUp(self):
certfn = os.path.join(TEST_DIR, 'testcert.pem')
self.certdir = os.path.join(TEST_DIR, 'testdata', 'certificate')
cacertfn = os.path.join(self.certdir, 'ca.crt')
self.httpd = compat_http_server.HTTPServer(('127.0.0.1', 0), HTTPTestRequestHandler)
self.httpd = http.server.HTTPServer(('127.0.0.1', 0), HTTPTestRequestHandler)
sslctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
sslctx.verify_mode = ssl.CERT_REQUIRED
sslctx.load_verify_locations(cafile=cacertfn)
@ -130,7 +132,7 @@ def test_certificate_nocombined_pass(self):
def _build_proxy_handler(name):
class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
class HTTPTestRequestHandler(http.server.BaseHTTPRequestHandler):
proxy_name = name
def log_message(self, format, *args):
@ -146,14 +148,14 @@ def do_GET(self):
class TestProxy(unittest.TestCase):
def setUp(self):
self.proxy = compat_http_server.HTTPServer(
self.proxy = http.server.HTTPServer(
('127.0.0.1', 0), _build_proxy_handler('normal'))
self.port = http_server_port(self.proxy)
self.proxy_thread = threading.Thread(target=self.proxy.serve_forever)
self.proxy_thread.daemon = True
self.proxy_thread.start()
self.geo_proxy = compat_http_server.HTTPServer(
self.geo_proxy = http.server.HTTPServer(
('127.0.0.1', 0), _build_proxy_handler('geo'))
self.geo_port = http_server_port(self.geo_proxy)
self.geo_proxy_thread = threading.Thread(target=self.geo_proxy.serve_forever)
@ -170,7 +172,7 @@ def test_proxy(self):
response = ydl.urlopen(url).read().decode()
self.assertEqual(response, f'normal: {url}')
req = compat_urllib_request.Request(url)
req = urllib.request.Request(url)
req.add_header('Ytdl-request-proxy', geo_proxy)
response = ydl.urlopen(req).read().decode()
self.assertEqual(response, f'geo: {url}')

9
test/test_socks.py
View file

@ -8,9 +8,10 @@
import random
import subprocess
from test.helper import FakeYDL, get_params, is_download_test
import urllib.request
from yt_dlp.compat import compat_str, compat_urllib_request
from test.helper import FakeYDL, get_params, is_download_test
from yt_dlp.compat import compat_str
@is_download_test
@ -51,7 +52,7 @@ def test_secondary_proxy_http(self):
if params is None:
return
ydl = FakeYDL()
req = compat_urllib_request.Request('http://yt-dl.org/ip')
req = urllib.request.Request('http://yt-dl.org/ip')
req.add_header('Ytdl-request-proxy', params['secondary_proxy'])
self.assertEqual(
ydl.urlopen(req).read().decode(),
@ -62,7 +63,7 @@ def test_secondary_proxy_https(self):
if params is None:
return
ydl = FakeYDL()
req = compat_urllib_request.Request('https://yt-dl.org/ip')
req = urllib.request.Request('https://yt-dl.org/ip')
req.add_header('Ytdl-request-proxy', params['secondary_proxy'])
self.assertEqual(
ydl.urlopen(req).read().decode(),

2
test/test_subtitles.py
View file

@ -6,8 +6,8 @@
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import FakeYDL, is_download_test, md5
from test.helper import FakeYDL, is_download_test, md5
from yt_dlp.extractor import (
NPOIE,
NRKTVIE,

17
test/test_utils.py
View file

@ -15,12 +15,9 @@
import xml.etree.ElementTree
from yt_dlp.compat import (
compat_chr,
compat_etree_fromstring,
compat_getenv,
compat_HTMLParseError,
compat_os_name,
compat_setenv,
)
from yt_dlp.utils import (
Config,
@ -266,20 +263,20 @@ def test_expand_path(self):
def env(var):
return f'%{var}%' if sys.platform == 'win32' else f'${var}'
compat_setenv('yt_dlp_EXPATH_PATH', 'expanded')
os.environ['yt_dlp_EXPATH_PATH'] = 'expanded'
self.assertEqual(expand_path(env('yt_dlp_EXPATH_PATH')), 'expanded')
old_home = os.environ.get('HOME')
test_str = R'C:\Documents and Settings\тест\Application Data'
try:
compat_setenv('HOME', test_str)
self.assertEqual(expand_path(env('HOME')), compat_getenv('HOME'))
self.assertEqual(expand_path('~'), compat_getenv('HOME'))
os.environ['HOME'] = test_str
self.assertEqual(expand_path(env('HOME')), os.getenv('HOME'))
self.assertEqual(expand_path('~'), os.getenv('HOME'))
self.assertEqual(
expand_path('~/%s' % env('yt_dlp_EXPATH_PATH')),
'%s/expanded' % compat_getenv('HOME'))
'%s/expanded' % os.getenv('HOME'))
finally:
compat_setenv('HOME', old_home or '')
os.environ['HOME'] = old_home or ''
def test_prepend_extension(self):
self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
@ -1128,7 +1125,7 @@ def test_extract_attributes(self):
self.assertEqual(extract_attributes('<e x="décompose&#769;">'), {'x': 'décompose\u0301'})
# "Narrow" Python builds don't support unicode code points outside BMP.
try:
compat_chr(0x10000)
chr(0x10000)
supports_outside_bmp = True
except ValueError:
supports_outside_bmp = False

21
yt_dlp/YoutubeDL.py
View file

@ -26,15 +26,8 @@
from string import ascii_letters
from .cache import Cache
from .compat import (
HAS_LEGACY as compat_has_legacy,
compat_get_terminal_size,
compat_os_name,
compat_shlex_quote,
compat_str,
compat_urllib_error,
compat_urllib_request,
)
from .compat import HAS_LEGACY as compat_has_legacy
from .compat import compat_os_name, compat_shlex_quote, compat_str
from .cookies import load_cookies
from .downloader import FFmpegFD, get_suitable_downloader, shorten_protocol_name
from .downloader.rtmp import rtmpdump_version
@ -644,7 +637,7 @@ def check_deprecated(param, option, suggestion):
try:
import pty
master, slave = pty.openpty()
width = compat_get_terminal_size().columns
width = shutil.get_terminal_size().columns
width_args = [] if width is None else ['-w', str(width)]
sp_kwargs = {'stdin': subprocess.PIPE, 'stdout': slave, 'stderr': self._out_files.error}
try:
@ -3724,7 +3717,7 @@ def _setup_opener(self):
else:
proxies = {'http': opts_proxy, 'https': opts_proxy}
else:
proxies = compat_urllib_request.getproxies()
proxies = urllib.request.getproxies()
# Set HTTPS proxy to HTTP one if given (https://github.com/ytdl-org/youtube-dl/issues/805)
if 'http' in proxies and 'https' not in proxies:
proxies['https'] = proxies['http']
@ -3740,13 +3733,13 @@ def _setup_opener(self):
# default FileHandler and allows us to disable the file protocol, which
# can be used for malicious purposes (see
# https://github.com/ytdl-org/youtube-dl/issues/8227)
file_handler = compat_urllib_request.FileHandler()
file_handler = urllib.request.FileHandler()
def file_open(*args, **kwargs):
raise compat_urllib_error.URLError('file:// scheme is explicitly disabled in yt-dlp for security reasons')
raise urllib.error.URLError('file:// scheme is explicitly disabled in yt-dlp for security reasons')
file_handler.file_open = file_open
opener = compat_urllib_request.build_opener(
opener = urllib.request.build_opener(
proxy_handler, https_handler, cookie_processor, ydlh, redirect_handler, data_handler, file_handler)
# Delete the default user-agent header, which would otherwise apply in

7
yt_dlp/__init__.py
View file

@ -3,13 +3,14 @@
__license__ = 'Public Domain'
import getpass
import itertools
import optparse
import os
import re
import sys
from .compat import compat_getpass, compat_shlex_quote
from .compat import compat_shlex_quote
from .cookies import SUPPORTED_BROWSERS, SUPPORTED_KEYRINGS
from .downloader import FileDownloader
from .downloader.external import get_external_downloader
@ -531,9 +532,9 @@ def report_deprecation(val, old, new=None):
# Ask for passwords
if opts.username is not None and opts.password is None:
opts.password = compat_getpass('Type account password and press [Return]: ')
opts.password = getpass.getpass('Type account password and press [Return]: ')
if opts.ap_username is not None and opts.ap_password is None:
opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
opts.ap_password = getpass.getpass('Type TV provider account password and press [Return]: ')
return warnings, deprecation_warnings

3
yt_dlp/cache.py
View file

@ -6,7 +6,6 @@
import shutil
import traceback
from .compat import compat_getenv
from .utils import expand_path, write_json_file
@ -17,7 +16,7 @@ def __init__(self, ydl):
def _get_root_dir(self):
res = self._ydl.params.get('cachedir')
if res is None:
cache_root = compat_getenv('XDG_CACHE_HOME', '~/.cache')
cache_root = os.getenv('XDG_CACHE_HOME', '~/.cache')
res = os.path.join(cache_root, 'yt-dlp')
return expand_path(res)

48
yt_dlp/compat/_deprecated.py
View file

@ -1,52 +1,16 @@
"""Deprecated - New code should avoid these"""
import base64
import getpass
import html
import html.parser
import http
import http.client
import http.cookiejar
import http.cookies
import http.server
import itertools
import os
import shutil
import struct
import tokenize
import urllib
import urllib.error
import urllib.parse
compat_str = str
compat_b64decode = base64.b64decode
compat_chr = chr
compat_cookiejar = http.cookiejar
compat_cookiejar_Cookie = http.cookiejar.Cookie
compat_cookies_SimpleCookie = http.cookies.SimpleCookie
compat_get_terminal_size = shutil.get_terminal_size
compat_getenv = os.getenv
compat_getpass = getpass.getpass
compat_html_entities = html.entities
compat_html_entities_html5 = html.entities.html5
compat_HTMLParser = html.parser.HTMLParser
compat_http_client = http.client
compat_http_server = http.server
compat_HTTPError = urllib.error.HTTPError
compat_itertools_count = itertools.count
compat_urlparse = urllib.parse
compat_parse_qs = urllib.parse.parse_qs
compat_str = str
compat_struct_pack = struct.pack
compat_struct_unpack = struct.unpack
compat_tokenize_tokenize = tokenize.tokenize
compat_urllib_error = urllib.error
compat_urllib_parse_unquote = urllib.parse.unquote
compat_urllib_parse_unquote_plus = urllib.parse.unquote_plus
compat_urllib_parse_urlencode = urllib.parse.urlencode
compat_urllib_parse_urlparse = urllib.parse.urlparse
compat_urllib_request = urllib.request
compat_urlparse = compat_urllib_parse = urllib.parse
def compat_setenv(key, value, env=os.environ):
env[key] = value
__all__ = [x for x in globals() if x.startswith('compat_')]

36
yt_dlp/compat/_legacy.py
View file

@ -2,15 +2,23 @@
import collections
import ctypes
import http
import getpass
import html.entities
import html.parser
import http.client
import http.cookiejar
import http.cookies
import http.server
import itertools
import os
import shlex
import shutil
import socket
import struct
import urllib
import tokenize
import urllib.error
import urllib.parse
import urllib.request
import xml.etree.ElementTree as etree
from subprocess import DEVNULL
@ -32,12 +40,17 @@ def compat_ctypes_WINFUNCTYPE(*args, **kwargs):
return ctypes.WINFUNCTYPE(*args, **kwargs)
def compat_setenv(key, value, env=os.environ):
env[key] = value
compat_basestring = str
compat_collections_abc = collections.abc
compat_cookies = http.cookies
compat_etree_Element = etree.Element
compat_etree_register_namespace = etree.register_namespace
compat_filter = filter
compat_getenv = os.getenv
compat_input = input
compat_integer_types = (int, )
compat_kwargs = lambda kwargs: kwargs
@ -53,9 +66,28 @@ def compat_ctypes_WINFUNCTYPE(*args, **kwargs):
compat_urllib_parse_unquote_to_bytes = urllib.parse.unquote_to_bytes
compat_urllib_parse_urlunparse = urllib.parse.urlunparse
compat_urllib_request_DataHandler = urllib.request.DataHandler
compat_urllib_request = urllib.request
compat_urllib_response = urllib.response
compat_urlretrieve = urllib.request.urlretrieve
compat_xml_parse_error = etree.ParseError
compat_xpath = lambda xpath: xpath
compat_zip = zip
workaround_optparse_bug9161 = lambda: None
compat_getpass = getpass.getpass
compat_chr = chr
compat_urllib_parse = urllib.parse
compat_itertools_count = itertools.count
compat_cookiejar = http.cookiejar
compat_cookiejar_Cookie = http.cookiejar.Cookie
compat_cookies_SimpleCookie = http.cookies.SimpleCookie
compat_get_terminal_size = shutil.get_terminal_size
compat_html_entities = html.entities
compat_html_entities_html5 = html.entities.html5
compat_tokenize_tokenize = tokenize.tokenize
compat_HTMLParser = html.parser.HTMLParser
compat_http_client = http.client
compat_http_server = http.server
compat_struct_pack = struct.pack
compat_struct_unpack = struct.unpack
compat_urllib_error = urllib.error
compat_urllib_parse_unquote_plus = urllib.parse.unquote_plus

9
yt_dlp/cookies.py
View file

@ -11,13 +11,14 @@
from datetime import datetime, timedelta, timezone
from enum import Enum, auto
from hashlib import pbkdf2_hmac
import http.cookiejar
from .aes import (
aes_cbc_decrypt_bytes,
aes_gcm_decrypt_and_verify_bytes,
unpad_pkcs7,
)
from .compat import compat_b64decode, compat_cookiejar_Cookie
from .compat import compat_b64decode
from .dependencies import (
_SECRETSTORAGE_UNAVAILABLE_REASON,
secretstorage,
@ -142,7 +143,7 @@ def _extract_firefox_cookies(profile, logger):
total_cookie_count = len(table)
for i, (host, name, value, path, expiry, is_secure) in enumerate(table):
progress_bar.print(f'Loading cookie {i: 6d}/{total_cookie_count: 6d}')
cookie = compat_cookiejar_Cookie(
cookie = http.cookiejar.Cookie(
version=0, name=name, value=value, port=None, port_specified=False,
domain=host, domain_specified=bool(host), domain_initial_dot=host.startswith('.'),
path=path, path_specified=bool(path), secure=is_secure, expires=expiry, discard=False,
@ -297,7 +298,7 @@ def _process_chrome_cookie(decryptor, host_key, name, value, encrypted_value, pa
if value is None:
return is_encrypted, None
return is_encrypted, compat_cookiejar_Cookie(
return is_encrypted, http.cookiejar.Cookie(
version=0, name=name, value=value, port=None, port_specified=False,
domain=host_key, domain_specified=bool(host_key), domain_initial_dot=host_key.startswith('.'),
path=path, path_specified=bool(path), secure=is_secure, expires=expires_utc, discard=False,
@ -589,7 +590,7 @@ def _parse_safari_cookies_record(data, jar, logger):
p.skip_to(record_size, 'space at the end of the record')
cookie = compat_cookiejar_Cookie(
cookie = http.cookiejar.Cookie(
version=0, name=name, value=value, port=None, port_specified=False,
domain=domain, domain_specified=bool(domain), domain_initial_dot=domain.startswith('.'),
path=path, path_specified=bool(path), secure=is_secure, expires=expiration_date, discard=False,

5
yt_dlp/downloader/external.py
View file

@ -7,7 +7,6 @@
from .fragment import FragmentFD
from ..compat import functools # isort: split
from ..compat import compat_setenv
from ..postprocessor.ffmpeg import EXT_TO_OUT_FORMATS, FFmpegPostProcessor
from ..utils import (
Popen,
@ -403,8 +402,8 @@ def _call_downloader(self, tmpfilename, info_dict):
# We could switch to the following code if we are able to detect version properly
# args += ['-http_proxy', proxy]
env = os.environ.copy()
compat_setenv('HTTP_PROXY', proxy, env=env)
compat_setenv('http_proxy', proxy, env=env)
env['HTTP_PROXY'] = proxy
env['http_proxy'] = proxy
protocol = info_dict.get('protocol')

17
yt_dlp/downloader/f4m.py
View file

@ -1,14 +1,13 @@
import io
import itertools
import struct
import time
import urllib.error
from .fragment import FragmentFD
from ..compat import (
compat_b64decode,
compat_etree_fromstring,
compat_struct_pack,
compat_struct_unpack,
compat_urllib_error,
compat_urllib_parse_urlparse,
compat_urlparse,
)
@ -35,13 +34,13 @@ def read_bytes(self, n):
# Utility functions for reading numbers and strings
def read_unsigned_long_long(self):
return compat_struct_unpack('!Q', self.read_bytes(8))[0]
return struct.unpack('!Q', self.read_bytes(8))[0]
def read_unsigned_int(self):
return compat_struct_unpack('!I', self.read_bytes(4))[0]
return struct.unpack('!I', self.read_bytes(4))[0]
def read_unsigned_char(self):
return compat_struct_unpack('!B', self.read_bytes(1))[0]
return struct.unpack('!B', self.read_bytes(1))[0]
def read_string(self):
res = b''
@ -203,11 +202,11 @@ def build_fragments_list(boot_info):
def write_unsigned_int(stream, val):
stream.write(compat_struct_pack('!I', val))
stream.write(struct.pack('!I', val))
def write_unsigned_int_24(stream, val):
stream.write(compat_struct_pack('!I', val)[1:])
stream.write(struct.pack('!I', val)[1:])
def write_flv_header(stream):
@ -411,7 +410,7 @@ def real_download(self, filename, info_dict):
if box_type == b'mdat':
self._append_fragment(ctx, box_data)
break
except compat_urllib_error.HTTPError as err:
except urllib.error.HTTPError as err:
if live and (err.code == 404 or err.code == 410):
# We didn't keep up with the live window. Continue
# with the next available fragment.

8
yt_dlp/downloader/fragment.py
View file

@ -4,12 +4,14 @@
import json
import math
import os
import struct
import time
import urllib.error
from .common import FileDownloader
from .http import HttpFD
from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
from ..compat import compat_os_name, compat_struct_pack, compat_urllib_error
from ..compat import compat_os_name
from ..utils import (
DownloadError,
encodeFilename,
@ -348,7 +350,7 @@ def decrypt_fragment(fragment, frag_content):
decrypt_info = fragment.get('decrypt_info')
if not decrypt_info or decrypt_info['METHOD'] != 'AES-128':
return frag_content
iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', fragment['media_sequence'])
iv = decrypt_info.get('IV') or struct.pack('>8xq', fragment['media_sequence'])
decrypt_info['KEY'] = decrypt_info.get('KEY') or _get_key(info_dict.get('_decryption_key_url') or decrypt_info['URI'])
# Don't decrypt the content in tests since the data is explicitly truncated and it's not to a valid block
# size (see https://github.com/ytdl-org/youtube-dl/pull/27660). Tests only care that the correct data downloaded,
@ -457,7 +459,7 @@ def download_fragment(fragment, ctx):
if self._download_fragment(ctx, fragment['url'], info_dict, headers):
break
return
except (compat_urllib_error.HTTPError, http.client.IncompleteRead) as err:
except (urllib.error.HTTPError, http.client.IncompleteRead) as err:
# Unavailable (possibly temporary) fragments may be served.
# First we try to retry then either skip or abort.
# See https://github.com/ytdl-org/youtube-dl/issues/10165,

11
yt_dlp/downloader/http.py
View file

@ -3,9 +3,10 @@
import socket
import ssl
import time
import urllib.error
import http.client
from .common import FileDownloader
from ..compat import compat_http_client, compat_urllib_error
from ..utils import (
ContentTooShortError,
ThrottledDownload,
@ -24,7 +25,7 @@
socket.timeout, # compat: py < 3.10
ConnectionError,
ssl.SSLError,
compat_http_client.HTTPException
http.client.HTTPException
)
@ -155,7 +156,7 @@ def establish_connection():
ctx.resume_len = 0
ctx.open_mode = 'wb'
ctx.data_len = ctx.content_len = int_or_none(ctx.data.info().get('Content-length', None))
except compat_urllib_error.HTTPError as err:
except urllib.error.HTTPError as err:
if err.code == 416:
# Unable to resume (requested range not satisfiable)
try:
@ -163,7 +164,7 @@ def establish_connection():
ctx.data = self.ydl.urlopen(
sanitized_Request(url, request_data, headers))
content_length = ctx.data.info()['Content-Length']
except compat_urllib_error.HTTPError as err:
except urllib.error.HTTPError as err:
if err.code < 500 or err.code >= 600:
raise
else:
@ -196,7 +197,7 @@ def establish_connection():
# Unexpected HTTP error
raise
raise RetryDownload(err)
except compat_urllib_error.URLError as err:
except urllib.error.URLError as err:
if isinstance(err.reason, ssl.CertificateError):
raise
raise RetryDownload(err)

4
yt_dlp/downloader/ism.py
View file

@ -2,9 +2,9 @@
import io
import struct
import time
import urllib.error
from .fragment import FragmentFD
from ..compat import compat_urllib_error
u8 = struct.Struct('>B')
u88 = struct.Struct('>Bx')
@ -268,7 +268,7 @@ def real_download(self, filename, info_dict):
extra_state['ism_track_written'] = True
self._append_fragment(ctx, frag_content)
break
except compat_urllib_error.HTTPError as err:
except urllib.error.HTTPError as err:
count += 1
if count <= fragment_retries:
self.report_retry_fragment(err, frag_index, count, fragment_retries)

4
yt_dlp/downloader/youtube_live_chat.py
View file

@ -1,8 +1,8 @@
import json
import time
import urllib.error
from .fragment import FragmentFD
from ..compat import compat_urllib_error
from ..utils import RegexNotFoundError, dict_get, int_or_none, try_get
@ -128,7 +128,7 @@ def download_and_parse_fragment(url, frag_index, request_data=None, headers=None
elif info_dict['protocol'] == 'youtube_live_chat':
continuation_id, offset, click_tracking_params = parse_actions_live(live_chat_continuation)
return True, continuation_id, offset, click_tracking_params
except compat_urllib_error.HTTPError as err:
except urllib.error.HTTPError as err:
count += 1
if count <= fragment_retries:
self.report_retry_fragment(err, frag_index, count, fragment_retries)

9
yt_dlp/extractor/abematv.py
View file

@ -7,12 +7,13 @@
import re
import struct
import time
import urllib.request
import urllib.response
import uuid
from .common import InfoExtractor
from ..aes import aes_ecb_decrypt
from ..compat import compat_urllib_parse_urlparse, compat_urllib_request
from ..compat import compat_urllib_parse_urlparse
from ..utils import (
ExtractorError,
bytes_to_intlist,
@ -33,7 +34,7 @@ def add_opener(ydl, handler):
''' Add a handler for opening URLs, like _download_webpage '''
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L426
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L605
assert isinstance(ydl._opener, compat_urllib_request.OpenerDirector)
assert isinstance(ydl._opener, urllib.request.OpenerDirector)
ydl._opener.add_handler(handler)
@ -46,7 +47,7 @@ def remove_opener(ydl, handler):
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L426
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L605
opener = ydl._opener
assert isinstance(ydl._opener, compat_urllib_request.OpenerDirector)
assert isinstance(ydl._opener, urllib.request.OpenerDirector)
if isinstance(handler, (type, tuple)):
find_cp = lambda x: isinstance(x, handler)
else:
@ -96,7 +97,7 @@ def remove_opener(ydl, handler):
opener.handlers[:] = [x for x in opener.handlers if not find_cp(x)]
class AbemaLicenseHandler(compat_urllib_request.BaseHandler):
class AbemaLicenseHandler(urllib.request.BaseHandler):
handler_order = 499
STRTABLE = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz'
HKEY = b'3AF0298C219469522A313570E8583005A642E73EDD58E3EA2FB7339D3DF1597E'

17
yt_dlp/extractor/adobepass.py
View file

@ -1,3 +1,4 @@
import getpass
import json
import re
import time
@ -5,19 +6,15 @@
import xml.etree.ElementTree as etree
from .common import InfoExtractor
from ..compat import (
compat_urlparse,
compat_getpass
)
from ..compat import compat_urlparse
from ..utils import (
unescapeHTML,
urlencode_postdata,
unified_timestamp,
ExtractorError,
NO_DEFAULT,
ExtractorError,
unescapeHTML,
unified_timestamp,
urlencode_postdata,
)
MSO_INFO = {
'DTV': {
'name': 'DIRECTV',
@ -1506,7 +1503,7 @@ def extract_redirect_url(html, url=None, fatal=False):
'send_confirm_link': False,
'send_token': True
}))
philo_code = compat_getpass('Type auth code you have received [Return]: ')
philo_code = getpass.getpass('Type auth code you have received [Return]: ')
self._download_webpage(
'https://idp.philo.com/auth/update/login_code', video_id, 'Submitting token', data=urlencode_postdata({
'token': philo_code

24
yt_dlp/extractor/archiveorg.py
View file

@ -1,36 +1,34 @@
import re
import json
import re
import urllib.parse
from .common import InfoExtractor
from .youtube import YoutubeIE, YoutubeBaseInfoExtractor
from ..compat import (
compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus,
compat_HTTPError
)
from .youtube import YoutubeBaseInfoExtractor, YoutubeIE
from ..compat import compat_HTTPError, compat_urllib_parse_unquote
from ..utils import (
KNOWN_EXTENSIONS,
ExtractorError,
HEADRequest,
bug_reports_message,
clean_html,
dict_get,
extract_attributes,
ExtractorError,
get_element_by_id,
HEADRequest,
int_or_none,
join_nonempty,
KNOWN_EXTENSIONS,
merge_dicts,
mimetype2ext,
orderedSet,
parse_duration,
parse_qs,
str_to_int,
str_or_none,
str_to_int,
traverse_obj,
try_get,
unified_strdate,
unified_timestamp,
url_or_none,
urlhandle_detect_ext,
url_or_none
)
@ -143,7 +141,7 @@ def _playlist_data(webpage):
return json.loads(extract_attributes(element)['value'])
def _real_extract(self, url):
video_id = compat_urllib_parse_unquote_plus(self._match_id(url))
video_id = urllib.parse.unquote_plus(self._match_id(url))
identifier, entry_id = (video_id.split('/', 1) + [None])[:2]
# Archive.org metadata API doesn't clearly demarcate playlist entries

12
yt_dlp/extractor/bbc.py
View file

@ -1,16 +1,12 @@
import xml.etree.ElementTree
import functools
import itertools
import json
import re
import urllib.error
import xml.etree.ElementTree
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_str,
compat_urllib_error,
compat_urlparse,
)
from ..compat import compat_HTTPError, compat_str, compat_urlparse
from ..utils import (
ExtractorError,
OnDemandPagedList,
@ -391,7 +387,7 @@ def _process_media_selector(self, media_selection, programme_id):
href, programme_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id=format_id, fatal=False)
except ExtractorError as e:
if not (isinstance(e.exc_info[1], compat_urllib_error.HTTPError)
if not (isinstance(e.exc_info[1], urllib.error.HTTPError)
and e.exc_info[1].code in (403, 404)):
raise
fmts = []

12
yt_dlp/extractor/cda.py
View file

@ -1,13 +1,9 @@
import codecs
import re
import json
import re
from .common import InfoExtractor
from ..compat import (
compat_chr,
compat_ord,
compat_urllib_parse_unquote,
)
from ..compat import compat_ord, compat_urllib_parse_unquote
from ..utils import (
ExtractorError,
float_or_none,
@ -16,8 +12,8 @@
multipart_encode,
parse_duration,
random_birthday,
urljoin,
try_get,
urljoin,
)
@ -144,7 +140,7 @@ def decrypt_file(a):
b = []
for c in a:
f = compat_ord(c)
b.append(compat_chr(33 + (f + 14) % 94) if 33 <= f <= 126 else compat_chr(f))
b.append(chr(33 + (f + 14) % 94) if 33 <= f <= 126 else chr(f))
a = ''.join(b)
a = a.replace('.cda.mp4', '')
for p in ('.2cda.pl', '.3cda.pl'):

8
yt_dlp/extractor/chingari.py
View file

@ -1,11 +1,11 @@
import itertools
import json
import urllib.parse
from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote_plus
from ..utils import (
clean_html,
ExtractorError,
clean_html,
int_or_none,
str_to_int,
url_or_none,
@ -47,8 +47,8 @@ def _get_post(self, id, post_data):
'id': id,
'extractor_key': ChingariIE.ie_key(),
'extractor': 'Chingari',
'title': compat_urllib_parse_unquote_plus(clean_html(post_data.get('caption'))),
'description': compat_urllib_parse_unquote_plus(clean_html(post_data.get('caption'))),
'title': urllib.parse.unquote_plus(clean_html(post_data.get('caption'))),
'description': urllib.parse.unquote_plus(clean_html(post_data.get('caption'))),
'duration': media_data.get('duration'),
'thumbnail': url_or_none(thumbnail),
'like_count': post_data.get('likeCount'),

31
yt_dlp/extractor/common.py
View file

@ -1,5 +1,6 @@
import base64
import collections
import getpass
import hashlib
import itertools
import json
@ -9,22 +10,20 @@
import random
import sys
import time
import urllib.request
import xml.etree.ElementTree
import http.client
import http.cookiejar
import http.cookies
from ..compat import functools, re # isort: split
from ..compat import (
compat_cookiejar_Cookie,
compat_cookies_SimpleCookie,
compat_etree_fromstring,
compat_expanduser,
compat_getpass,
compat_http_client,
compat_os_name,
compat_str,
compat_urllib_error,
compat_urllib_parse_unquote,
compat_urllib_parse_urlencode,
compat_urllib_request,
compat_urlparse,
)
from ..downloader import FileDownloader
@ -671,7 +670,7 @@ def extract(self, url):
if hasattr(e, 'countries'):
kwargs['countries'] = e.countries
raise type(e)(e.orig_msg, **kwargs)
except compat_http_client.IncompleteRead as e:
except http.client.IncompleteRead as e:
raise ExtractorError('A network error has occurred.', cause=e, expected=True, video_id=self.get_temp_id(url))
except (KeyError, StopIteration) as e:
raise ExtractorError('An extractor error has occurred.', cause=e, video_id=self.get_temp_id(url))
@ -730,7 +729,7 @@ def IE_NAME(cls):
@staticmethod
def __can_accept_status_code(err, expected_status):
assert isinstance(err, compat_urllib_error.HTTPError)
assert isinstance(err, urllib.error.HTTPError)
if expected_status is None:
return False
elif callable(expected_status):
@ -739,7 +738,7 @@ def __can_accept_status_code(err, expected_status):
return err.code in variadic(expected_status)
def _create_request(self, url_or_request, data=None, headers={}, query={}):
if isinstance(url_or_request, compat_urllib_request.Request):
if isinstance(url_or_request, urllib.request.Request):
return update_Request(url_or_request, data=data, headers=headers, query=query)
if query:
url_or_request = update_url_query(url_or_request, query)
@ -779,7 +778,7 @@ def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fa
try:
return self._downloader.urlopen(self._create_request(url_or_request, data, headers, query))
except network_exceptions as err:
if isinstance(err, compat_urllib_error.HTTPError):
if isinstance(err, urllib.error.HTTPError):
if self.__can_accept_status_code(err, expected_status):
# Retain reference to error to prevent file object from
# being closed before it can be read. Works around the
@ -807,7 +806,7 @@ def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=
Arguments:
url_or_request -- plain text URL as a string or
a compat_urllib_request.Requestobject
a urllib.request.Request object
video_id -- Video/playlist/item identifier (string)
Keyword arguments:
@ -1056,7 +1055,7 @@ def _download_webpage(
while True:
try:
return self.__download_webpage(url_or_request, video_id, note, errnote, None, fatal, *args, **kwargs)
except compat_http_client.IncompleteRead as e:
except http.client.IncompleteRead as e:
try_count += 1
if try_count >= tries:
raise e
@ -1292,7 +1291,7 @@ def _get_tfa_info(self, note='two-factor verification code'):
if tfa is not None:
return tfa
return compat_getpass('Type %s and press [Return]: ' % note)
return getpass.getpass('Type %s and press [Return]: ' % note)
# Helper functions for extracting OpenGraph info
@staticmethod
@ -3597,15 +3596,15 @@ def _float(self, v, name, fatal=False, **kwargs):
def _set_cookie(self, domain, name, value, expire_time=None, port=None,
path='/', secure=False, discard=False, rest={}, **kwargs):
cookie = compat_cookiejar_Cookie(
cookie = http.cookiejar.Cookie(
0, name, value, port, port is not None, domain, True,
domain.startswith('.'), path, True, secure, expire_time,
discard, None, None, rest)
self.cookiejar.set_cookie(cookie)
def _get_cookies(self, url):
""" Return a compat_cookies_SimpleCookie with the cookies for the url """
return compat_cookies_SimpleCookie(self._downloader._calc_cookies(url))
""" Return a http.cookies.SimpleCookie with the cookies for the url """
return http.cookies.SimpleCookie(self._downloader._calc_cookies(url))
def _apply_first_set_cookie_header(self, url_handle, cookie):
"""

18
yt_dlp/extractor/crunchyroll.py
View file

@ -1,19 +1,20 @@
import base64
import re
import json
import zlib
import re
import urllib.request
import xml.etree.ElementTree
import zlib
from hashlib import sha1
from math import pow, sqrt, floor
from math import floor, pow, sqrt
from .common import InfoExtractor
from .vrv import VRVBaseIE
from ..aes import aes_cbc_decrypt
from ..compat import (
compat_b64decode,
compat_etree_fromstring,
compat_str,
compat_urllib_parse_urlencode,
compat_urllib_request,
compat_urlparse,
)
from ..utils import (
@ -22,8 +23,8 @@
extract_attributes,
float_or_none,
format_field,
intlist_to_bytes,
int_or_none,
intlist_to_bytes,
join_nonempty,
lowercase_escape,
merge_dicts,
@ -34,9 +35,6 @@
try_get,
xpath_text,
)
from ..aes import (
aes_cbc_decrypt,
)
class CrunchyrollBaseIE(InfoExtractor):
@ -259,7 +257,7 @@ class CrunchyrollIE(CrunchyrollBaseIE, VRVBaseIE):
}
def _download_webpage(self, url_or_request, *args, **kwargs):
request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request)
request = (url_or_request if isinstance(url_or_request, urllib.request.Request)
else sanitized_Request(url_or_request))
# Accept-Language must be set explicitly to accept any language to avoid issues
# similar to https://github.com/ytdl-org/youtube-dl/issues/6797.

2
yt_dlp/extractor/espn.py
View file

@ -1,7 +1,7 @@
import base64
import json
import re
import urllib
import urllib.parse
from .common import InfoExtractor
from .adobepass import AdobePassIE

6
yt_dlp/extractor/facebook.py
View file

@ -1,18 +1,18 @@
import json
import re
import urllib.parse
from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
compat_str,
compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus,
)
from ..utils import (
ExtractorError,
clean_html,
determine_ext,
error_to_compat_str,
ExtractorError,
float_or_none,
get_element_by_id,
get_first,
@ -467,7 +467,7 @@ def extract_dash_manifest(video, formats):
dash_manifest = video.get('dash_manifest')
if dash_manifest:
formats.extend(self._parse_mpd_formats(
compat_etree_fromstring(compat_urllib_parse_unquote_plus(dash_manifest))))
compat_etree_fromstring(urllib.parse.unquote_plus(dash_manifest))))
def process_formats(formats):
# Downloads with browser's User-Agent are rate limited. Working around

2
yt_dlp/extractor/iwara.py
View file

@ -1,6 +1,6 @@
import itertools
import re
import urllib
import urllib.parse
from .common import InfoExtractor
from ..utils import (

6
yt_dlp/extractor/kusi.py
View file

@ -1,10 +1,10 @@
import random
import urllib.parse
from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote_plus
from ..utils import (
int_or_none,
float_or_none,
int_or_none,
timeconvert,
update_url_query,
xpath_text,
@ -66,7 +66,7 @@ def _real_extract(self, url):
formats = []
for quality in quality_options:
formats.append({
'url': compat_urllib_parse_unquote_plus(quality.attrib['url']),
'url': urllib.parse.unquote_plus(quality.attrib['url']),
'height': int_or_none(quality.attrib.get('height')),
'width': int_or_none(quality.attrib.get('width')),
'vbr': float_or_none(quality.attrib.get('bitratebits'), scale=1000),

13
yt_dlp/extractor/metacafe.py
View file

@ -1,17 +1,14 @@
import json
import re
import urllib.parse
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_parse,
compat_urllib_parse_unquote,
)
from ..compat import compat_parse_qs, compat_urllib_parse_unquote
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
determine_ext,
get_element_by_attribute,
int_or_none,
mimetype2ext,
)
@ -143,7 +140,7 @@ def _real_extract(self, url):
headers = {
# Disable family filter
'Cookie': 'user=%s; ' % compat_urllib_parse.quote(json.dumps({'ffilter': False}))
'Cookie': 'user=%s; ' % urllib.parse.quote(json.dumps({'ffilter': False}))
}
# AnyClip videos require the flashversion cookie so that we get the link

3
yt_dlp/extractor/mixcloud.py
View file

@ -3,7 +3,6 @@
from .common import InfoExtractor
from ..compat import (
compat_b64decode,
compat_chr,
compat_ord,
compat_str,
compat_urllib_parse_unquote,
@ -72,7 +71,7 @@ class MixcloudIE(MixcloudBaseIE):
def _decrypt_xor_cipher(key, ciphertext):
"""Encrypt/Decrypt XOR cipher. Both ways are possible because it's XOR."""
return ''.join([
compat_chr(compat_ord(ch) ^ compat_ord(k))
chr(compat_ord(ch) ^ compat_ord(k))
for ch, k in zip(ciphertext, itertools.cycle(key))])
def _real_extract(self, url):

14
yt_dlp/extractor/ndtv.py
View file

@ -1,13 +1,7 @@
import urllib.parse
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_unquote_plus
)
from ..utils import (
parse_duration,
remove_end,
unified_strdate,
urljoin
)
from ..utils import parse_duration, remove_end, unified_strdate, urljoin
class NDTVIE(InfoExtractor):
@ -80,7 +74,7 @@ def _real_extract(self, url):
webpage = self._download_webpage(url, video_id)
# '__title' does not contain extra words such as sub-site name, "Video" etc.
title = compat_urllib_parse_unquote_plus(
title = urllib.parse.unquote_plus(
self._search_regex(r"__title\s*=\s*'([^']+)'", webpage, 'title', default=None)
or self._og_search_title(webpage))

9
yt_dlp/extractor/nebula.py
View file

@ -1,14 +1,11 @@
import itertools
import json
import time
import urllib
import urllib.parse
import urllib.error
from ..utils import (
ExtractorError,
parse_iso8601,
try_get,
)
from .common import InfoExtractor
from ..utils import ExtractorError, parse_iso8601, try_get
class NebulaBaseIE(InfoExtractor):

18
yt_dlp/extractor/neteasemusic.py
View file

@ -1,18 +1,12 @@
from hashlib import md5
import itertools
import re
from base64 import b64encode
from datetime import datetime
import re
from hashlib import md5
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlencode,
compat_str,
compat_itertools_count,
)
from ..utils import (
sanitized_Request,
float_or_none,
)
from ..compat import compat_str, compat_urllib_parse_urlencode
from ..utils import float_or_none, sanitized_Request
class NetEaseMusicBaseIE(InfoExtractor):
@ -449,7 +443,7 @@ def _real_extract(self, url):
name = None
desc = None
entries = []
for offset in compat_itertools_count(start=0, step=self._PAGE_SIZE):
for offset in itertools.count(start=0, step=self._PAGE_SIZE):
info = self.query_api(
'dj/program/byradio?asc=false&limit=%d&radioId=%s&offset=%d'
% (self._PAGE_SIZE, dj_id, offset),

12
yt_dlp/extractor/peloton.py
View file

@ -1,11 +1,9 @@
import json
import re
import urllib.parse
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_urllib_parse,
)
from ..compat import compat_HTTPError
from ..utils import (
ExtractorError,
float_or_none,
@ -125,7 +123,7 @@ def _real_extract(self, url):
is_live = False
if ride_data.get('content_format') == 'audio':
url = self._MANIFEST_URL_TEMPLATE % (ride_data.get('vod_stream_url'), compat_urllib_parse.quote(token))
url = self._MANIFEST_URL_TEMPLATE % (ride_data.get('vod_stream_url'), urllib.parse.quote(token))
formats = [{
'url': url,
'ext': 'm4a',
@ -138,9 +136,9 @@ def _real_extract(self, url):
url = 'https://members.onepeloton.com/.netlify/functions/m3u8-proxy?displayLanguage=en&acceptedSubtitles=%s&url=%s?hdnea=%s' % (
','.join([re.sub('^([a-z]+)-([A-Z]+)$', r'\1', caption) for caption in ride_data['captions']]),
ride_data['vod_stream_url'],
compat_urllib_parse.quote(compat_urllib_parse.quote(token)))
urllib.parse.quote(urllib.parse.quote(token)))
elif ride_data.get('live_stream_url'):
url = self._MANIFEST_URL_TEMPLATE % (ride_data.get('live_stream_url'), compat_urllib_parse.quote(token))
url = self._MANIFEST_URL_TEMPLATE % (ride_data.get('live_stream_url'), urllib.parse.quote(token))
is_live = True
else:
raise ExtractorError('Missing video URL')

13
yt_dlp/extractor/playvid.py
View file

@ -1,14 +1,9 @@
import re
import urllib.parse
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus,
)
from ..utils import (
clean_html,
ExtractorError,
)
from ..compat import compat_urllib_parse_unquote
from ..utils import ExtractorError, clean_html
class PlayvidIE(InfoExtractor):
@ -62,7 +57,7 @@ def _real_extract(self, url):
val = videovars_match.group(2)
if key == 'title':
video_title = compat_urllib_parse_unquote_plus(val)
video_title = urllib.parse.unquote_plus(val)
if key == 'duration':
try:
duration = int(val)

7
yt_dlp/extractor/popcorntimes.py
View file

@ -1,8 +1,5 @@
from .common import InfoExtractor
from ..compat import (
compat_b64decode,
compat_chr,
)
from ..compat import compat_b64decode
from ..utils import int_or_none
@ -50,7 +47,7 @@ def _real_extract(self, url):
c_ord += 13
if upper < c_ord:
c_ord -= 26
loc_b64 += compat_chr(c_ord)
loc_b64 += chr(c_ord)
video_url = compat_b64decode(loc_b64).decode('utf-8')

15
yt_dlp/extractor/pornhub.py
View file

@ -3,29 +3,26 @@
import math
import operator
import re
import urllib.request
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_str,
compat_urllib_request,
)
from .openload import PhantomJSwrapper
from ..compat import compat_HTTPError, compat_str
from ..utils import (
NO_DEFAULT,
ExtractorError,
clean_html,
determine_ext,
ExtractorError,
format_field,
int_or_none,
merge_dicts,
NO_DEFAULT,
orderedSet,
remove_quotes,
remove_start,
str_to_int,
update_url_query,
urlencode_postdata,
url_or_none,
urlencode_postdata,
)
@ -50,7 +47,7 @@ def dl(*args, **kwargs):
r'document\.location\.reload\(true\)')):
url_or_request = args[0]
url = (url_or_request.get_full_url()
if isinstance(url_or_request, compat_urllib_request.Request)
if isinstance(url_or_request, urllib.request.Request)
else url_or_request)
phantom = PhantomJSwrapper(self, required_version='2.0')
phantom.get(url, html=webpage)

10
yt_dlp/extractor/rtve.py
View file

@ -1,14 +1,12 @@
import base64
import io
import struct
from .common import InfoExtractor
from ..compat import (
compat_b64decode,
compat_struct_unpack,
)
from ..compat import compat_b64decode
from ..utils import (
determine_ext,
ExtractorError,
determine_ext,
float_or_none,
qualities,
remove_end,
@ -73,7 +71,7 @@ def _real_initialize(self):
def _decrypt_url(png):
encrypted_data = io.BytesIO(compat_b64decode(png)[8:])
while True:
length = compat_struct_unpack('!I', encrypted_data.read(4))[0]
length = struct.unpack('!I', encrypted_data.read(4))[0]
chunk_type = encrypted_data.read(4)
if chunk_type == b'IEND':
break

13
yt_dlp/extractor/screencast.py
View file

@ -1,11 +1,8 @@
import urllib.request
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_request,
)
from ..utils import (
ExtractorError,
)
from ..compat import compat_parse_qs
from ..utils import ExtractorError
class ScreencastIE(InfoExtractor):
@ -75,7 +72,7 @@ def _real_extract(self, url):
flash_vars_s = flash_vars_s.replace(',', '&')
if flash_vars_s:
flash_vars = compat_parse_qs(flash_vars_s)
video_url_raw = compat_urllib_request.quote(
video_url_raw = urllib.request.quote(
flash_vars['content'][0])
video_url = video_url_raw.replace('http%3A', 'http:')

15
yt_dlp/extractor/shared.py
View file

@ -1,14 +1,15 @@
import urllib.parse
from .common import InfoExtractor
from ..compat import (
compat_b64decode,
compat_urllib_parse_unquote_plus,
)
from ..compat import compat_b64decode
from ..utils import (
determine_ext,
KNOWN_EXTENSIONS,
ExtractorError,
determine_ext,
int_or_none,
js_to_json,
KNOWN_EXTENSIONS,
parse_filesize,
rot47,
url_or_none,
@ -130,7 +131,7 @@ def decode_url_old(encoded_url):
return stream_url
def decode_url(encoded_url):
return rot47(compat_urllib_parse_unquote_plus(encoded_url))
return rot47(urllib.parse.unquote_plus(encoded_url))
return decode_url(self._parse_json(
self._search_regex(

12
yt_dlp/extractor/udemy.py
View file

@ -1,16 +1,12 @@
import re
import urllib.request
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_str,
compat_urllib_request,
compat_urlparse,
)
from ..compat import compat_HTTPError, compat_str, compat_urlparse
from ..utils import (
ExtractorError,
determine_ext,
extract_attributes,
ExtractorError,
float_or_none,
int_or_none,
js_to_json,
@ -155,7 +151,7 @@ def _download_json(self, url_or_request, *args, **kwargs):
headers['X-Udemy-Bearer-Token'] = cookie.value
headers['X-Udemy-Authorization'] = 'Bearer %s' % cookie.value
if isinstance(url_or_request, compat_urllib_request.Request):
if isinstance(url_or_request, urllib.request.Request):
for header, value in headers.items():
url_or_request.add_header(header, value)
else:

13
yt_dlp/extractor/urort.py
View file

@ -1,10 +1,9 @@
import urllib.parse
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
)
from ..utils import (
unified_strdate,
)
from ..utils import unified_strdate
class UrortIE(InfoExtractor):
@ -31,7 +30,7 @@ class UrortIE(InfoExtractor):
def _real_extract(self, url):
playlist_id = self._match_id(url)
fstr = compat_urllib_parse.quote("InternalBandUrl eq '%s'" % playlist_id)
fstr = urllib.parse.quote("InternalBandUrl eq '%s'" % playlist_id)
json_url = 'http://urort.p3.no/breeze/urort/TrackDTOViews?$filter=%s&$orderby=Released%%20desc&$expand=Tags%%2CFiles' % fstr
songs = self._download_json(json_url, playlist_id)
entries = []

9
yt_dlp/extractor/videa.py
View file

@ -1,8 +1,10 @@
import random
import re
import string
import struct
from .common import InfoExtractor
from ..compat import compat_b64decode, compat_ord
from ..utils import (
ExtractorError,
int_or_none,
@ -14,11 +16,6 @@
xpath_element,
xpath_text,
)
from ..compat import (
compat_b64decode,
compat_ord,
compat_struct_pack,
)
class VideaIE(InfoExtractor):
@ -102,7 +99,7 @@ def rc4(cipher_text, key):
j = (j + S[i]) % 256
S[i], S[j] = S[j], S[i]
k = S[(S[i] + S[j]) % 256]
res += compat_struct_pack('B', k ^ compat_ord(cipher_text[m]))
res += struct.pack('B', k ^ compat_ord(cipher_text[m]))
return res.decode()

15
yt_dlp/extractor/vrv.py
View file

@ -1,17 +1,14 @@
import base64
import json
import hashlib
import hmac
import json
import random
import string
import time
import urllib.parse
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_urllib_parse_urlencode,
compat_urllib_parse,
)
from ..compat import compat_HTTPError, compat_urllib_parse_urlencode
from ..utils import (
ExtractorError,
float_or_none,
@ -46,12 +43,12 @@ def _call_api(self, path, video_id, note, data=None):
headers['Content-Type'] = 'application/json'
base_string = '&'.join([
'POST' if data else 'GET',
compat_urllib_parse.quote(base_url, ''),
compat_urllib_parse.quote(encoded_query, '')])
urllib.parse.quote(base_url, ''),
urllib.parse.quote(encoded_query, '')])
oauth_signature = base64.b64encode(hmac.new(
(self._API_PARAMS['oAuthSecret'] + '&' + self._TOKEN_SECRET).encode('ascii'),
base_string.encode(), hashlib.sha1).digest()).decode()
encoded_query += '&oauth_signature=' + compat_urllib_parse.quote(oauth_signature, '')
encoded_query += '&oauth_signature=' + urllib.parse.quote(oauth_signature, '')
try:
return self._download_json(
'?'.join([base_url, encoded_query]), video_id,

8
yt_dlp/extractor/vshare.py
View file

@ -1,11 +1,7 @@
import re
from .common import InfoExtractor
from ..compat import compat_chr
from ..utils import (
decode_packed_codes,
ExtractorError,
)
from ..utils import ExtractorError, decode_packed_codes
class VShareIE(InfoExtractor):
@ -37,7 +33,7 @@ def _extract_packed(self, webpage):
digits = [int(digit) for digit in digits.split(',')]
key_digit = self._search_regex(
r'fromCharCode\(.+?(\d+)\)}', unpacked, 'key digit')
chars = [compat_chr(d - int(key_digit)) for d in digits]
chars = [chr(d - int(key_digit)) for d in digits]
return ''.join(chars)
def _real_extract(self, url):

7
yt_dlp/extractor/xfileshare.py
View file

@ -1,11 +1,10 @@
import re
from .common import InfoExtractor
from ..compat import compat_chr
from ..utils import (
ExtractorError,
decode_packed_codes,
determine_ext,
ExtractorError,
int_or_none,
js_to_json,
urlencode_postdata,
@ -32,11 +31,11 @@ def aa_decode(aa_code):
aa_char = aa_char.replace('+ ', '')
m = re.match(r'^\d+', aa_char)
if m:
ret += compat_chr(int(m.group(0), 8))
ret += chr(int(m.group(0), 8))
else:
m = re.match(r'^u([\da-f]+)', aa_char)
if m:
ret += compat_chr(int(m.group(1), 16))
ret += chr(int(m.group(1), 16))
return ret

15
yt_dlp/extractor/yahoo.py
View file

@ -1,15 +1,15 @@
import hashlib
import itertools
import re
import urllib.parse
from .brightcove import BrightcoveNewIE
from .common import InfoExtractor, SearchInfoExtractor
from ..compat import (
compat_str,
compat_urllib_parse,
)
from .youtube import YoutubeIE
from ..compat import compat_str
from ..utils import (
clean_html,
ExtractorError,
clean_html,
int_or_none,
mimetype2ext,
parse_iso8601,
@ -18,9 +18,6 @@
url_or_none,
)
from .brightcove import BrightcoveNewIE
from .youtube import YoutubeIE
class YahooIE(InfoExtractor):
IE_DESC = 'Yahoo screen and movies'
@ -333,7 +330,7 @@ class YahooSearchIE(SearchInfoExtractor):
def _search_results(self, query):
for pagenum in itertools.count(0):
result_url = 'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30)
result_url = 'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (urllib.parse.quote_plus(query), pagenum * 30)
info = self._download_json(result_url, query,
note='Downloading results page ' + str(pagenum + 1))
yield from (self.url_result(result['rurl']) for result in info['results'])

6
yt_dlp/extractor/ynet.py
View file

@ -1,8 +1,8 @@
import re
import json
import re
import urllib.parse
from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote_plus
class YnetIE(InfoExtractor):
@ -31,7 +31,7 @@ def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
content = compat_urllib_parse_unquote_plus(self._og_search_video_url(webpage))
content = urllib.parse.unquote_plus(self._og_search_video_url(webpage))
config = json.loads(self._search_regex(r'config=({.+?})$', content, 'video config'))
f4m_url = config['clip']['url']
title = self._og_search_title(webpage)

11
yt_dlp/extractor/youtube.py
View file

@ -13,15 +13,14 @@
import threading
import time
import traceback
import urllib.parse
from .common import InfoExtractor, SearchInfoExtractor
from ..compat import functools # isort: split
from ..compat import (
compat_chr,
compat_HTTPError,
compat_parse_qs,
compat_str,
compat_urllib_parse_unquote_plus,
compat_urllib_parse_urlencode,
compat_urllib_parse_urlparse,
compat_urlparse,
@ -2483,7 +2482,7 @@ def _extract_signature_function(self, video_id, player_url, example_sig):
if code:
res = self._parse_sig_js(code)
test_string = ''.join(map(compat_chr, range(len(example_sig))))
test_string = ''.join(map(chr, range(len(example_sig))))
cache_res = res(test_string)
cache_spec = [ord(c) for c in cache_res]
@ -2522,7 +2521,7 @@ def _genslice(start, end, step):
else:
yield _genslice(start, i, step)
test_string = ''.join(map(compat_chr, range(len(example_sig))))
test_string = ''.join(map(chr, range(len(example_sig))))
cache_res = func(test_string)
cache_spec = [ord(c) for c in cache_res]
expr_code = ' + '.join(gen_sig_code(cache_spec))
@ -3421,7 +3420,7 @@ def _real_extract(self, url):
# fields may contain comma as well (see
# https://github.com/ytdl-org/youtube-dl/issues/8536)
feed_data = compat_parse_qs(
compat_urllib_parse_unquote_plus(feed))
urllib.parse.unquote_plus(feed))
def feed_entry(name):
return try_get(
@ -5846,7 +5845,7 @@ def _real_extract(self, url):
if params:
section = next((k for k, v in self._SECTIONS.items() if v == params), params)
else:
section = compat_urllib_parse_unquote_plus((url.split('#') + [''])[1]).lower()
section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
params = self._SECTIONS.get(section)
if not params:
section = None

9
yt_dlp/options.py
View file

@ -4,10 +4,11 @@
import os.path
import re
import shlex
import shutil
import string
import sys
from .compat import compat_expanduser, compat_get_terminal_size, compat_getenv
from .compat import compat_expanduser
from .cookies import SUPPORTED_BROWSERS, SUPPORTED_KEYRINGS
from .downloader.external import list_external_downloaders
from .postprocessor import (
@ -39,7 +40,7 @@ def parseOpts(overrideArguments=None, ignore_config_files='if_override'):
def _readUserConf(package_name, default=[]):
# .config
xdg_config_home = compat_getenv('XDG_CONFIG_HOME') or compat_expanduser('~/.config')
xdg_config_home = os.getenv('XDG_CONFIG_HOME') or compat_expanduser('~/.config')
userConfFile = os.path.join(xdg_config_home, package_name, 'config')
if not os.path.isfile(userConfFile):
userConfFile = os.path.join(xdg_config_home, '%s.conf' % package_name)
@ -48,7 +49,7 @@ def _readUserConf(package_name, default=[]):
return userConf, userConfFile
# appdata
appdata_dir = compat_getenv('appdata')
appdata_dir = os.getenv('appdata')
if appdata_dir:
userConfFile = os.path.join(appdata_dir, package_name, 'config')
userConf = Config.read_file(userConfFile, default=None)
@ -137,7 +138,7 @@ def load_configs():
class _YoutubeDLHelpFormatter(optparse.IndentedHelpFormatter):
def __init__(self):
# No need to wrap help messages if we're on a wide console
max_width = compat_get_terminal_size().columns or 80
max_width = shutil.get_terminal_size().columns or 80
# The % is chosen to get a pretty output in README.md
super().__init__(width=max_width, max_help_position=int(0.45 * max_width))

31
yt_dlp/socks.py
View file

@ -8,8 +8,9 @@
import collections
import socket
import struct
from .compat import compat_ord, compat_struct_pack, compat_struct_unpack
from .compat import compat_ord
__author__ = 'Timo Schmid <coding@timoschmid.de>'
@ -19,7 +20,7 @@
# if the client cannot resolve the destination host's domain name to find its
# IP address, it should set the first three bytes of DSTIP to NULL and the last
# byte to a non-zero value.
SOCKS4_DEFAULT_DSTIP = compat_struct_pack('!BBBB', 0, 0, 0, 0xFF)
SOCKS4_DEFAULT_DSTIP = struct.pack('!BBBB', 0, 0, 0, 0xFF)
SOCKS5_VERSION = 5
SOCKS5_USER_AUTH_VERSION = 0x01
@ -122,11 +123,11 @@ def recvall(self, cnt):
def _recv_bytes(self, cnt):
data = self.recvall(cnt)
return compat_struct_unpack(f'!{cnt}B', data)
return struct.unpack(f'!{cnt}B', data)
@staticmethod
def _len_and_data(data):
return compat_struct_pack('!B', len(data)) + data
return struct.pack('!B', len(data)) + data
def _check_response_version(self, expected_version, got_version):
if got_version != expected_version:
@ -147,7 +148,7 @@ def _setup_socks4(self, address, is_4a=False):
ipaddr = self._resolve_address(destaddr, SOCKS4_DEFAULT_DSTIP, use_remote_dns=is_4a)
packet = compat_struct_pack('!BBH', SOCKS4_VERSION, Socks4Command.CMD_CONNECT, port) + ipaddr
packet = struct.pack('!BBH', SOCKS4_VERSION, Socks4Command.CMD_CONNECT, port) + ipaddr
username = (self._proxy.username or '').encode()
packet += username + b'\x00'
@ -157,7 +158,7 @@ def _setup_socks4(self, address, is_4a=False):
self.sendall(packet)
version, resp_code, dstport, dsthost = compat_struct_unpack('!BBHI', self.recvall(8))
version, resp_code, dstport, dsthost = struct.unpack('!BBHI', self.recvall(8))
self._check_response_version(SOCKS4_REPLY_VERSION, version)
@ -171,14 +172,14 @@ def _setup_socks4a(self, address):
self._setup_socks4(address, is_4a=True)
def _socks5_auth(self):
packet = compat_struct_pack('!B', SOCKS5_VERSION)
packet = struct.pack('!B', SOCKS5_VERSION)
auth_methods = [Socks5Auth.AUTH_NONE]
if self._proxy.username and self._proxy.password:
auth_methods.append(Socks5Auth.AUTH_USER_PASS)
packet += compat_struct_pack('!B', len(auth_methods))
packet += compat_struct_pack(f'!{len(auth_methods)}B', *auth_methods)
packet += struct.pack('!B', len(auth_methods))
packet += struct.pack(f'!{len(auth_methods)}B', *auth_methods)
self.sendall(packet)
@ -194,7 +195,7 @@ def _socks5_auth(self):
if method == Socks5Auth.AUTH_USER_PASS:
username = self._proxy.username.encode()
password = self._proxy.password.encode()
packet = compat_struct_pack('!B', SOCKS5_USER_AUTH_VERSION)
packet = struct.pack('!B', SOCKS5_USER_AUTH_VERSION)
packet += self._len_and_data(username) + self._len_and_data(password)
self.sendall(packet)
@ -214,14 +215,14 @@ def _setup_socks5(self, address):
self._socks5_auth()
reserved = 0
packet = compat_struct_pack('!BBB', SOCKS5_VERSION, Socks5Command.CMD_CONNECT, reserved)
packet = struct.pack('!BBB', SOCKS5_VERSION, Socks5Command.CMD_CONNECT, reserved)
if ipaddr is None:
destaddr = destaddr.encode()
packet += compat_struct_pack('!B', Socks5AddressType.ATYP_DOMAINNAME)
packet += struct.pack('!B', Socks5AddressType.ATYP_DOMAINNAME)
packet += self._len_and_data(destaddr)
else:
packet += compat_struct_pack('!B', Socks5AddressType.ATYP_IPV4) + ipaddr
packet += compat_struct_pack('!H', port)
packet += struct.pack('!B', Socks5AddressType.ATYP_IPV4) + ipaddr
packet += struct.pack('!H', port)
self.sendall(packet)
@ -240,7 +241,7 @@ def _setup_socks5(self, address):
destaddr = self.recvall(alen)
elif atype == Socks5AddressType.ATYP_IPV6:
destaddr = self.recvall(16)
destport = compat_struct_unpack('!H', self.recvall(2))[0]
destport = struct.unpack('!H', self.recvall(2))[0]
return (destaddr, destport)

124
yt_dlp/utils.py
View file

@ -14,6 +14,8 @@
import gzip
import hashlib
import hmac
import html.entities
import html.parser
import importlib.util
import io
import itertools
@ -29,6 +31,7 @@
import shlex
import socket
import ssl
import struct
import subprocess
import sys
import tempfile
@ -36,35 +39,27 @@
import traceback
import types
import urllib.parse
import urllib.request
import xml.etree.ElementTree
import zlib
import http.client
import http.cookiejar
from .compat import asyncio, functools # isort: split
from .compat import (
compat_chr,
compat_cookiejar,
compat_etree_fromstring,
compat_expanduser,
compat_html_entities,
compat_html_entities_html5,
compat_HTMLParseError,
compat_HTMLParser,
compat_http_client,
compat_HTTPError,
compat_os_name,
compat_parse_qs,
compat_shlex_quote,
compat_str,
compat_struct_pack,
compat_struct_unpack,
compat_urllib_error,
compat_urllib_parse_unquote_plus,
compat_urllib_parse_urlencode,
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urlparse,
)
from .dependencies import brotli, certifi, websockets
from .dependencies import brotli, certifi, websockets, xattr
from .socks import ProxyType, sockssocket
@ -445,7 +440,7 @@ def get_elements_text_and_html_by_attribute(attribute, value, html, escape_value
)
class HTMLBreakOnClosingTagParser(compat_HTMLParser):
class HTMLBreakOnClosingTagParser(html.parser.HTMLParser):
"""
HTML parser which raises HTMLBreakOnClosingTagException upon reaching the
closing tag for the first opening tag it has encountered, and can be used
@ -457,7 +452,7 @@ class HTMLBreakOnClosingTagException(Exception):
def __init__(self):
self.tagstack = collections.deque()
compat_HTMLParser.__init__(self)
html.parser.HTMLParser.__init__(self)
def __enter__(self):
return self
@ -522,22 +517,22 @@ def find_or_raise(haystack, needle, exc):
raise compat_HTMLParseError('unexpected end of html')
class HTMLAttributeParser(compat_HTMLParser):
class HTMLAttributeParser(html.parser.HTMLParser):
"""Trivial HTML parser to gather the attributes for a single element"""
def __init__(self):
self.attrs = {}
compat_HTMLParser.__init__(self)
html.parser.HTMLParser.__init__(self)
def handle_starttag(self, tag, attrs):
self.attrs = dict(attrs)
class HTMLListAttrsParser(compat_HTMLParser):
class HTMLListAttrsParser(html.parser.HTMLParser):
"""HTML parser to gather the attributes for the elements of a list"""
def __init__(self):
compat_HTMLParser.__init__(self)
html.parser.HTMLParser.__init__(self)
self.items = []
self._level = 0
@ -763,7 +758,7 @@ def sanitized_Request(url, *args, **kwargs):
if auth_header is not None:
headers = args[1] if len(args) >= 2 else kwargs.setdefault('headers', {})
headers['Authorization'] = auth_header
return compat_urllib_request.Request(url, *args, **kwargs)
return urllib.request.Request(url, *args, **kwargs)
def expand_path(s):
@ -788,13 +783,13 @@ def _htmlentity_transform(entity_with_semicolon):
entity = entity_with_semicolon[:-1]
# Known non-numeric HTML entity
if entity in compat_html_entities.name2codepoint:
return compat_chr(compat_html_entities.name2codepoint[entity])
if entity in html.entities.name2codepoint:
return chr(html.entities.name2codepoint[entity])
# TODO: HTML5 allows entities without a semicolon. For example,
# '&Eacuteric' should be decoded as 'Éric'.
if entity_with_semicolon in compat_html_entities_html5:
return compat_html_entities_html5[entity_with_semicolon]
if entity_with_semicolon in html.entities.html5:
return html.entities.html5[entity_with_semicolon]
mobj = re.match(r'#(x[0-9a-fA-F]+|[0-9]+)', entity)
if mobj is not None:
@ -806,7 +801,7 @@ def _htmlentity_transform(entity_with_semicolon):
base = 10
# See https://github.com/ytdl-org/youtube-dl/issues/7518
with contextlib.suppress(ValueError):
return compat_chr(int(numstr, base))
return chr(int(numstr, base))
# Unknown entity in name, return its literal representation
return '&%s;' % entity
@ -1015,7 +1010,7 @@ def __init__(self, msg=None):
super().__init__(self.msg)
network_exceptions = [compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error]
network_exceptions = [urllib.error.URLError, http.client.HTTPException, socket.error]
if hasattr(ssl, 'CertificateError'):
network_exceptions.append(ssl.CertificateError)
network_exceptions = tuple(network_exceptions)
@ -1267,7 +1262,7 @@ def handle_youtubedl_headers(headers):
return filtered_headers
class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
class YoutubeDLHandler(urllib.request.HTTPHandler):
"""Handler for HTTP requests and responses.
This class, when installed with an OpenerDirector, automatically adds
@ -1286,11 +1281,11 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
"""
def __init__(self, params, *args, **kwargs):
compat_urllib_request.HTTPHandler.__init__(self, *args, **kwargs)
urllib.request.HTTPHandler.__init__(self, *args, **kwargs)
self._params = params
def http_open(self, req):
conn_class = compat_http_client.HTTPConnection
conn_class = http.client.HTTPConnection
socks_proxy = req.headers.get('Ytdl-socks-proxy')
if socks_proxy:
@ -1365,18 +1360,18 @@ def http_response(self, req, resp):
break
else:
raise original_ioerror
resp = compat_urllib_request.addinfourl(uncompressed, old_resp.headers, old_resp.url, old_resp.code)
resp = urllib.request.addinfourl(uncompressed, old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
del resp.headers['Content-encoding']
# deflate
if resp.headers.get('Content-encoding', '') == 'deflate':
gz = io.BytesIO(self.deflate(resp.read()))
resp = compat_urllib_request.addinfourl(gz, old_resp.headers, old_resp.url, old_resp.code)
resp = urllib.request.addinfourl(gz, old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
del resp.headers['Content-encoding']
# brotli
if resp.headers.get('Content-encoding', '') == 'br':
resp = compat_urllib_request.addinfourl(
resp = urllib.request.addinfourl(
io.BytesIO(self.brotli(resp.read())), old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
del resp.headers['Content-encoding']
@ -1399,7 +1394,7 @@ def http_response(self, req, resp):
def make_socks_conn_class(base_class, socks_proxy):
assert issubclass(base_class, (
compat_http_client.HTTPConnection, compat_http_client.HTTPSConnection))
http.client.HTTPConnection, http.client.HTTPSConnection))
url_components = compat_urlparse.urlparse(socks_proxy)
if url_components.scheme.lower() == 'socks5':
@ -1412,7 +1407,7 @@ def make_socks_conn_class(base_class, socks_proxy):
def unquote_if_non_empty(s):
if not s:
return s
return compat_urllib_parse_unquote_plus(s)
return urllib.parse.unquote_plus(s)
proxy_args = (
socks_type,
@ -1430,7 +1425,7 @@ def connect(self):
self.sock.settimeout(self.timeout)
self.sock.connect((self.host, self.port))
if isinstance(self, compat_http_client.HTTPSConnection):
if isinstance(self, http.client.HTTPSConnection):
if hasattr(self, '_context'): # Python > 2.6
self.sock = self._context.wrap_socket(
self.sock, server_hostname=self.host)
@ -1440,10 +1435,10 @@ def connect(self):
return SocksConnection
class YoutubeDLHTTPSHandler(compat_urllib_request.HTTPSHandler):
class YoutubeDLHTTPSHandler(urllib.request.HTTPSHandler):
def __init__(self, params, https_conn_class=None, *args, **kwargs):
compat_urllib_request.HTTPSHandler.__init__(self, *args, **kwargs)
self._https_conn_class = https_conn_class or compat_http_client.HTTPSConnection
urllib.request.HTTPSHandler.__init__(self, *args, **kwargs)
self._https_conn_class = https_conn_class or http.client.HTTPSConnection
self._params = params
def https_open(self, req):
@ -1470,7 +1465,7 @@ def https_open(self, req):
raise
class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar):
class YoutubeDLCookieJar(http.cookiejar.MozillaCookieJar):
"""
See [1] for cookie file format.
@ -1541,7 +1536,7 @@ def save(self, filename=None, *args, **kwargs):
if self.filename is not None:
filename = self.filename
else:
raise ValueError(compat_cookiejar.MISSING_FILENAME_TEXT)
raise ValueError(http.cookiejar.MISSING_FILENAME_TEXT)
# Store session cookies with `expires` set to 0 instead of an empty string
for cookie in self:
@ -1558,7 +1553,7 @@ def load(self, filename=None, ignore_discard=False, ignore_expires=False):
if self.filename is not None:
filename = self.filename
else:
raise ValueError(compat_cookiejar.MISSING_FILENAME_TEXT)
raise ValueError(http.cookiejar.MISSING_FILENAME_TEXT)
def prepare_line(line):
if line.startswith(self._HTTPONLY_PREFIX):
@ -1568,10 +1563,10 @@ def prepare_line(line):
return line
cookie_list = line.split('\t')
if len(cookie_list) != self._ENTRY_LEN:
raise compat_cookiejar.LoadError('invalid length %d' % len(cookie_list))
raise http.cookiejar.LoadError('invalid length %d' % len(cookie_list))
cookie = self._CookieFileEntry(*cookie_list)
if cookie.expires_at and not cookie.expires_at.isdigit():
raise compat_cookiejar.LoadError('invalid expires at %s' % cookie.expires_at)
raise http.cookiejar.LoadError('invalid expires at %s' % cookie.expires_at)
return line
cf = io.StringIO()
@ -1579,9 +1574,9 @@ def prepare_line(line):
for line in f:
try:
cf.write(prepare_line(line))
except compat_cookiejar.LoadError as e:
except http.cookiejar.LoadError as e:
if f'{line.strip()} '[0] in '[{"':
raise compat_cookiejar.LoadError(
raise http.cookiejar.LoadError(
'Cookies file must be Netscape formatted, not JSON. See '
'https://github.com/ytdl-org/youtube-dl#how-do-i-pass-cookies-to-youtube-dl')
write_string(f'WARNING: skipping cookie file entry due to {e}: {line!r}\n')
@ -1604,18 +1599,18 @@ def prepare_line(line):
cookie.discard = True
class YoutubeDLCookieProcessor(compat_urllib_request.HTTPCookieProcessor):
class YoutubeDLCookieProcessor(urllib.request.HTTPCookieProcessor):
def __init__(self, cookiejar=None):
compat_urllib_request.HTTPCookieProcessor.__init__(self, cookiejar)
urllib.request.HTTPCookieProcessor.__init__(self, cookiejar)
def http_response(self, request, response):
return compat_urllib_request.HTTPCookieProcessor.http_response(self, request, response)
return urllib.request.HTTPCookieProcessor.http_response(self, request, response)
https_request = compat_urllib_request.HTTPCookieProcessor.http_request
https_request = urllib.request.HTTPCookieProcessor.http_request
https_response = http_response
class YoutubeDLRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
class YoutubeDLRedirectHandler(urllib.request.HTTPRedirectHandler):
"""YoutubeDL redirect handler
The code is based on HTTPRedirectHandler implementation from CPython [1].
@ -1630,7 +1625,7 @@ class YoutubeDLRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
3. https://github.com/ytdl-org/youtube-dl/issues/28768
"""
http_error_301 = http_error_303 = http_error_307 = http_error_308 = compat_urllib_request.HTTPRedirectHandler.http_error_302
http_error_301 = http_error_303 = http_error_307 = http_error_308 = urllib.request.HTTPRedirectHandler.http_error_302
def redirect_request(self, req, fp, code, msg, headers, newurl):
"""Return a Request or None in response to a redirect.
@ -1672,7 +1667,7 @@ def redirect_request(self, req, fp, code, msg, headers, newurl):
if code in (301, 302) and m == 'POST':
m = 'GET'
return compat_urllib_request.Request(
return urllib.request.Request(
newurl, headers=newheaders, origin_req_host=req.origin_req_host,
unverifiable=True, method=m)
@ -1967,7 +1962,7 @@ def bytes_to_intlist(bs):
def intlist_to_bytes(xs):
if not xs:
return b''
return compat_struct_pack('%dB' % len(xs), *xs)
return struct.pack('%dB' % len(xs), *xs)
class LockingUnsupportedError(OSError):
@ -2427,12 +2422,12 @@ def urljoin(base, path):
return compat_urlparse.urljoin(base, path)
class HEADRequest(compat_urllib_request.Request):
class HEADRequest(urllib.request.Request):
def get_method(self):
return 'HEAD'
class PUTRequest(compat_urllib_request.Request):
class PUTRequest(urllib.request.Request):
def get_method(self):
return 'PUT'
@ -2484,7 +2479,7 @@ def url_or_none(url):
def request_to_url(req):
if isinstance(req, compat_urllib_request.Request):
if isinstance(req, urllib.request.Request):
return req.get_full_url()
else:
return req
@ -3037,7 +3032,7 @@ def update_Request(req, url=None, data=None, headers={}, query={}):
elif req_get_method == 'PUT':
req_type = PUTRequest
else:
req_type = compat_urllib_request.Request
req_type = urllib.request.Request
new_req = req_type(
req_url, data=req_data, headers=req_headers,
origin_req_host=req.origin_req_host, unverifiable=req.unverifiable)
@ -4636,20 +4631,20 @@ def random_ipv4(cls, code_or_block):
else:
block = code_or_block
addr, preflen = block.split('/')
addr_min = compat_struct_unpack('!L', socket.inet_aton(addr))[0]
addr_min = struct.unpack('!L', socket.inet_aton(addr))[0]
addr_max = addr_min | (0xffffffff >> int(preflen))
return compat_str(socket.inet_ntoa(
compat_struct_pack('!L', random.randint(addr_min, addr_max))))
struct.pack('!L', random.randint(addr_min, addr_max))))
class PerRequestProxyHandler(compat_urllib_request.ProxyHandler):
class PerRequestProxyHandler(urllib.request.ProxyHandler):
def __init__(self, proxies=None):
# Set default handlers
for type in ('http', 'https'):
setattr(self, '%s_open' % type,
lambda r, proxy='__noproxy__', type=type, meth=self.proxy_open:
meth(r, proxy, type))
compat_urllib_request.ProxyHandler.__init__(self, proxies)
urllib.request.ProxyHandler.__init__(self, proxies)
def proxy_open(self, req, proxy, type):
req_proxy = req.headers.get('Ytdl-request-proxy')
@ -4663,7 +4658,7 @@ def proxy_open(self, req, proxy, type):
req.add_header('Ytdl-socks-proxy', proxy)
# yt-dlp's http/https handlers do wrapping the socket with socks
return None
return compat_urllib_request.ProxyHandler.proxy_open(
return urllib.request.ProxyHandler.proxy_open(
self, req, proxy, type)
@ -4683,7 +4678,7 @@ def long_to_bytes(n, blocksize=0):
s = b''
n = int(n)
while n > 0:
s = compat_struct_pack('>I', n & 0xffffffff) + s
s = struct.pack('>I', n & 0xffffffff) + s
n = n >> 32
# strip off leading zeros
for i in range(len(s)):
@ -4714,7 +4709,7 @@ def bytes_to_long(s):
s = b'\000' * extra + s
length = length + extra
for i in range(0, length, 4):
acc = (acc << 32) + compat_struct_unpack('>I', s[i:i + 4])[0]
acc = (acc << 32) + struct.unpack('>I', s[i:i + 4])[0]
return acc
@ -4842,7 +4837,7 @@ def decode_png(png_data):
raise OSError('Not a valid PNG file.')
int_map = {1: '>B', 2: '>H', 4: '>I'}
unpack_integer = lambda x: compat_struct_unpack(int_map[len(x)], x)[0]
unpack_integer = lambda x: struct.unpack(int_map[len(x)], x)[0]
chunks = []
@ -4954,7 +4949,6 @@ def write_xattr(path, key, value):
return
# UNIX Method 1. Use xattrs/pyxattrs modules
from .dependencies import xattr
setxattr = None
if getattr(xattr, '_yt_dlp__identifier', None) == 'pyxattr':